Schema | Knowledge Assistant MCP Server

Knowledge Assistant MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`RAG_TOP_K`	No	Number of chunks to retrieve (default: 5)	5
`MODEL_NAME`	No	Gemini model (default: gemini-2.0-flash)	gemini-2.0-flash
`OPIK_API_KEY`	No	Opik API key for observability – optional.
`GOOGLE_API_KEY`	Yes	Google AI (Gemini) API key – required. Get from Google AI Studio.
`EMBEDDING_MODEL`	No	Google embedding model for RAG (default: models/gemini-embedding-001)	models/gemini-embedding-001
`CHROMA_COLLECTION`	No	ChromaDB collection name (default: knowledge_base)	knowledge_base
`OPIK_PROJECT_NAME`	No	Opik project name (default: knowledge-assistant)	knowledge-assistant
`CHROMA_PERSIST_DIR`	No	ChromaDB persistence directory (default: ./chroma_data)	./chroma_data

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tasks`	{ "list": {}, "cancel": {}, "requests": { "tools": { "call": {} }, "prompts": { "get": {} }, "resources": { "read": {} } } }
`tools`	{ "listChanged": true }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
query_knowledge_baseA	Ask the knowledge assistant a question. Runs a multi-agent pipeline: coordinator -> retriever (RAG) -> synthesizer. Returns a proposed answer for your review. After reviewing, call approve_or_edit_answer to approve or request edits (human-in-the-loop).
approve_or_edit_answerA	Human-in-the-loop: approve the proposed answer from query_knowledge_base, or request edits. Set approved=True to accept, or approved=False and provide user_feedback for changes.
add_documentsA	Add a document (text) to the knowledge base. Use source to label where it came from.
search_knowledge_baseA	Search the knowledge base only (retriever); returns chunks without generating an answer.

Interactive templates invoked by user choice

Name	Description
`knowledge_assistant_workflow`	Multi-agent RAG workflow with human-in-the-loop: query → review proposal → approve or edit.

Contextual data attached and managed by the client

Name	Description
`server_info`	Server and knowledge base configuration (name, version, collection, RAG settings).

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SMGilliatt/knowledge-assistant-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server